{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3S23ESVB6K7XFWMZZFS37565QK","short_pith_number":"pith:3S23ESVB","schema_version":"1.0","canonical_sha256":"dcb5b24aa1f2bf72d999c965bff7dd82b1aac4c3353b94986ec95f048c7ff2dc","source":{"kind":"arxiv","id":"2312.07384","version":2},"attestation_state":"computed","paper":{"title":"Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Jiang, Hao Liu, Haoyu Tang, Kun Wang, Liqiang Nie, Yupeng Hu","submitted_at":"2023-12-12T16:00:55Z","abstract_excerpt":"Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2312.07384","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-12T16:00:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2f53f59f004c6d896960e6d22a9a2973f882192b68e90165ea78539fc1748e4b","abstract_canon_sha256":"ec9b7b18d29ec082461957038244500a3fa23fe7529b64424f0882a32c5c3120"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:11.159296Z","signature_b64":"oy28FcUIgWuMyuPWflrfbQLMD4ua5nosXc1whrOQ5sOfLIrGllSLkQW3R2fWqOgSoQKdyyL7j2HtGwZY4tfNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb5b24aa1f2bf72d999c965bff7dd82b1aac4c3353b94986ec95f048c7ff2dc","last_reissued_at":"2026-07-05T10:41:11.158797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:11.158797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Self-paced Iterative Learning for Unsupervised Temporal Action Localization","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Han Jiang, Hao Liu, Haoyu Tang, Kun Wang, Liqiang Nie, Yupeng Hu","submitted_at":"2023-12-12T16:00:55Z","abstract_excerpt":"Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and action categories, which is labor-intensive and time-consuming. Although some unsupervised methods have utilized the ``iteratively clustering and localization'' paradigm for TAL, they still suffer from two pivotal impediments: 1) unsatisfactory video clustering confidence, and 2) unreliable video pseudolabels for model training. To address these limitations, we"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.07384","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.07384/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2312.07384","created_at":"2026-07-05T10:41:11.158858+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.07384v2","created_at":"2026-07-05T10:41:11.158858+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.07384","created_at":"2026-07-05T10:41:11.158858+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S23ESVB6K7X","created_at":"2026-07-05T10:41:11.158858+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S23ESVB6K7XFWMZ","created_at":"2026-07-05T10:41:11.158858+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S23ESVB","created_at":"2026-07-05T10:41:11.158858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.19647","citing_title":"UTAL-GNN: Unsupervised Temporal Action Localization using Graph Neural Networks","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK","json":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK.json","graph_json":"https://pith.science/api/pith-number/3S23ESVB6K7XFWMZZFS37565QK/graph.json","events_json":"https://pith.science/api/pith-number/3S23ESVB6K7XFWMZZFS37565QK/events.json","paper":"https://pith.science/paper/3S23ESVB"},"agent_actions":{"view_html":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK","download_json":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK.json","view_paper":"https://pith.science/paper/3S23ESVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.07384&json=true","fetch_graph":"https://pith.science/api/pith-number/3S23ESVB6K7XFWMZZFS37565QK/graph.json","fetch_events":"https://pith.science/api/pith-number/3S23ESVB6K7XFWMZZFS37565QK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK/action/storage_attestation","attest_author":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK/action/author_attestation","sign_citation":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK/action/citation_signature","submit_replication":"https://pith.science/pith/3S23ESVB6K7XFWMZZFS37565QK/action/replication_record"}},"created_at":"2026-07-05T10:41:11.158858+00:00","updated_at":"2026-07-05T10:41:11.158858+00:00"}